mlsanityData to 7 Oct 2026

Subspace Attack: Exploiting Promising Subspaces for Query-Efficient Black-box Attacks

arXiv 1906.04392 ↗First posted 11 Jun 2019cs.CV cs.CR cs.LGcited by 35

Not on the map. Why?

Abstract (arXiv)

Unlike the white-box counterparts that are widely studied and readily accessible, adversarial examples in black-box settings are generally more Herculean on account of the difficulty of estimating gradients. Many methods achieve the task by issuing numerous queries to target classification systems, which makes the whole procedure costly and suspicious to the systems. In this paper, we aim at reducing the query complexity of black-box attacks in this category. We propose to exploit gradients of a few reference models which arguably span some promising search subspaces. Experimental results show that, in comparison with the state-of-the-arts, our method can gain up to 2x and 4x reductions in the requisite mean and medium numbers of queries with much lower failure rates even if the reference models are trained on a small and inadequate dataset disjoint to the one for training the victim model. Code and models for reproducing our results will be made publicly available.

Key facts. Cited by 35 papers in the map (data through 7 Oct 2026). First posted on arXiv 11 Jun 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 13; 2022: 8; 2023: 7; 2024: 4; 2025: 2; 2026: 1.

35 papers.

Sort:

By area:

  1. 2024PAL: Proxy-Guided Black-Box Attack on Large Language Modelscited by 46
  2. 2022Transferable Adversarial Attack based on Integrated Gradientscited by 35
  3. 2021A Review of Adversarial Attack and Defense for Classification Methodscited by 29
  4. 2023Generalizable Black-Box Adversarial Attack with Meta Learningcited by 29
  5. 2023Improving Adversarial Transferability via Intermediate-level Perturbation Decaycited by 29
  6. 2021QAIR: Practical Query-efficient Black-Box Attacks for Image Retrievalcited by 22
  7. 2021Just Noticeable Difference for Deep Machine Visioncited by 19
  8. 2023Attacks in Adversarial Machine Learning: A Systematic Survey from the Life-cycle Perspectivecited by 19
  9. 2023A Survey of Robustness and Safety of 2D and 3D Deep Learning Models Against Adversarial Attackscited by 19
  10. 2022Attacking deep networks with surrogate-based adversarial black-box methods is easycited by 18
  11. 2022Adversarial Attack on Attackers: Post-Process to Mitigate Black-Box Score-Based Query Attackscited by 18
  12. 2021On the Effectiveness of Small Input Noise for Defending Against Query-based Black-Box Attackscited by 17
23 more
  1. 2024Efficient Black-box Adversarial Attacks via Bayesian Optimization Guided by a Function Priorcited by 10
  2. 2021A Differentiable Language Model Adversarial Attack on Text Classifierscited by 9
  3. 2022An Intermediate-level Attack Framework on The Basis of Linear Regressioncited by 9
  4. 2023An End-to-End Framework for Marketing Effectiveness Optimization under Budget Constraintcited by 9
  5. 2021Progressive-Scale Boundary Blackbox Attack via Projective Gradient Estimationcited by 8
  6. 2022Practical No-box Adversarial Attacks with Training-free Hybrid Image Transformationcited by 8
  7. 2021Meta-Learning the Search Distribution of Black-Box Random Search Based Adversarial Attackscited by 7
  8. 2023SoK: Pitfalls in Evaluating Black-Box Attackscited by 6
  9. 2021Multi-stage Optimization based Adversarial Trainingcited by 4
  10. 2021Query Attack by Multi-Identity Surrogatescited by 3
  11. 2022Origins of Low-dimensional Adversarial Perturbationscited by 3
  12. 2021Adversarial Examples Detection with Bayesian Neural Networkcited by 2
  13. 2021Energy Attack: On Transferring Adversarial Examplescited by 2
  14. 2024DifAttack++: Query-Efficient Black-Box Adversarial Attack via Hierarchical Disentangled Feature Space in Cross-Domaincited by 2
  15. 2025GSBAK: top-K Geometric Score-based Black-box Attackcited by 2
  16. 2021Geometrically Adaptive Dictionary Attack on Face Recognitioncited by 1
  17. 2023DifAttack: Query-Efficient Black-Box Attack via Disentangled Feature Spacecited by 1
  18. 2024Sparse and Transferable Universal Singular Vectors Attackcited by 1
  19. 2021Generating Structured Adversarial Attacks Using Frank-Wolfe Methodcited by 0
  20. 2022Art-Attack: Black-Box Adversarial Attack via Evolutionary Artcited by 0
  21. 2022Cross-domain Cross-architecture Black-box Attacks on Fine-tuned Models with Transferred Evolutionary Strategiescited by 0
  22. 2025Exploiting Edge Features for Transferable Adversarial Attacks in Distributed Machine Learningcited by 0
  23. 2026CIVA: Critic-Induced Value-Subspace Attacks on Visual World-Model Agentscited by 0